Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2043 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.3049. Min Range: -1.3049
Max Act: 1.3049. Min Act: -0.1700
Data Index: 5030528 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3049. Min Range: -1.3049
Max Act: 1.1464. Min Act: -0.1700
Data Index: 7224211 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3049. Min Range: -1.3049
Max Act: 1.0937. Min Act: -0.1700
Data Index: 2294054 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3049. Min Range: -1.3049
Max Act: 1.0588. Min Act: -0.1700
Data Index: 5469969 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3049. Min Range: -1.3049
Max Act: 1.0588. Min Act: -0.1698
Data Index: 8633777 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3049. Min Range: -1.3049
Max Act: 1.0413. Min Act: -0.1700
Data Index: 291187 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3049. Min Range: -1.3049
Max Act: 1.0065. Min Act: -0.1700
Data Index: 6695188 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3049. Min Range: -1.3049
Max Act: 0.9718. Min Act: -0.1699
Data Index: 7903979 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3049. Min Range: -1.3049
Max Act: 0.9546. Min Act: -0.1676
Data Index: 4558215 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3049. Min Range: -1.3049
Max Act: 0.9546. Min Act: -0.1687
Data Index: 4918714 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3049. Min Range: -1.3049
Max Act: 0.9287. Min Act: -0.1700
Data Index: 1474471 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3049. Min Range: -1.3049
Max Act: 0.9287. Min Act: -0.1699
Data Index: 4111564 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3049. Min Range: -1.3049
Max Act: 0.9202. Min Act: -0.1696
Data Index: 6301620 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3049. Min Range: -1.3049
Max Act: 0.9202. Min Act: -0.1689
Data Index: 2450656 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3049. Min Range: -1.3049
Max Act: 0.9202. Min Act: -0.1696
Data Index: 5538021 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3049. Min Range: -1.3049
Max Act: 0.9287. Min Act: -0.1700
Data Index: 6341650 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3049. Min Range: -1.3049
Max Act: 0.9287. Min Act: -0.1698
Data Index: 6665345 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3049. Min Range: -1.3049
Max Act: 0.9287. Min Act: -0.1667
Data Index: 1026887 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3049. Min Range: -1.3049
Max Act: 0.9202. Min Act: -0.1700
Data Index: 4487400 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3049. Min Range: -1.3049
Max Act: 0.9373. Min Act: -0.1700
Data Index: 1420118 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #19